Dataset Information

Inter-laboratory automation of the in vitro micronucleus assay using imaging flow cytometry and deep learning.

ABSTRACT: The in vitro micronucleus assay is a globally significant method for DNA damage quantification used for regulatory compound safety testing in addition to inter-individual monitoring of environmental, lifestyle and occupational factors. However, it relies on time-consuming and user-subjective manual scoring. Here we show that imaging flow cytometry and deep learning image classification represents a capable platform for automated, inter-laboratory operation. Images were captured for the cytokinesis-block micronucleus (CBMN) assay across three laboratories using methyl methanesulphonate (1.25-5.0 μg/mL) and/or carbendazim (0.8-1.6 μg/mL) exposures to TK6 cells. Human-scored image sets were assembled and used to train and test the classification abilities of the "DeepFlow" neural network in both intra- and inter-laboratory contexts. Harnessing image diversity across laboratories yielded a network able to score unseen data from an entirely new laboratory without any user configuration. Image classification accuracies of 98%, 95%, 82% and 85% were achieved for 'mononucleates', 'binucleates', 'mononucleates with MN' and 'binucleates with MN', respectively. Successful classifications of 'trinucleates' (90%) and 'tetranucleates' (88%) in addition to 'other or unscorable' phenotypes (96%) were also achieved. Attempts to classify extremely rare, tri- and tetranucleated cells with micronuclei into their own categories were less successful (≤ 57%). Benchmark dose analyses of human or automatically scored micronucleus frequency data yielded quantitation of the same equipotent concentration regardless of scoring method. We conclude that this automated approach offers significant potential to broaden the practical utility of the CBMN method across industry, research and clinical domains. We share our strategy using openly-accessible frameworks.

SUBMITTER: Wills JW

PROVIDER: S-EPMC8380241 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Genetic toxicity testing assesses the potential of compounds to cause DNA damage. There are many genetic toxicology screening assays designed to assess the DNA damaging potential of chemicals in early drug development aiding the identification of promising drugs that have low-risk potential for causing genetic damage contributing to cancer risk in humans. Despite this, in vitro tests generate a high number of misleading positives, the consequences of which can lead to unnecessary animal testing and/or the abandonment of promising drug candidates. Understanding chemical Mode of Action (MoA) is vital to identifying the true genotoxic potential of substances and, therefore, the risk translation into the clinic. Here we demonstrate a simple, robust protocol for staining fixed, human-lymphoblast p53 proficient TK6 cells with antibodies against ɣH2AX, p53 and pH3S28 along with DRAQ5™ DNA staining that enables analysis of un-lysed cells via microscopy approaches such as imaging flow cytometry. Here, we used the Cytek® Amnis® ImageStream®X Mk II which provides a high-throughput acquisition platform with the sensitivity of flow cytometry and spatial morphological information associated with microscopy. Using the ImageStream manufacturer's software (IDEAS® 6.2), a masking strategy was developed to automatically detect and quantify micronucleus events (MN) and characterise biomarker populations. The gating strategy developed enables the generation of a template capable of automatically batch processing data files quantifying cell-cycle, MN, ɣH2AX, p53 and pH3 populations simultaneously. In this way, we demonstrate how a multiplex system enables DNA damage assessment alongside MN identification using un-lysed cells on the imaging flow cytometry platform. As a proof-of-concept, we use the tool chemicals carbendazim and methyl methanesulphonate (MMS) to demonstrate the assay's ability to correctly identify clastogenic or aneugenic MoAs using the biomarker profiles established.

Dataset Information

Inter-laboratory automation of the in vitro micronucleus assay using imaging flow cytometry and deep learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets